Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2750 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3865. Min Range: -1.3865

Max Act: 1.3865. Min Act: -0.0001

Data Index: 110672 (C4 (Web Text))

Max Activating Token Index: 747

Text #1

Max Range: 1.3865. Min Range: -1.3865

Max Act: 1.0281. Min Act: -0.0001

Data Index: 95843 (C4 (Web Text))

Max Activating Token Index: 659

Text #2

Max Range: 1.3865. Min Range: -1.3865

Max Act: 1.2675. Min Act: -0.0001

Data Index: 410525 (C4 (Web Text))

Max Activating Token Index: 14

Text #3

Max Range: 1.3865. Min Range: -1.3865

Max Act: 1.1356. Min Act: -0.0001

Data Index: 1295427 (C4 (Web Text))

Max Activating Token Index: 680

Text #4

Max Range: 1.3865. Min Range: -1.3865

Max Act: 1.2132. Min Act: -0.0001

Data Index: 1101297 (C4 (Web Text))

Max Activating Token Index: 53

Text #5

Max Range: 1.3865. Min Range: -1.3865

Max Act: 1.2059. Min Act: -0.0001

Data Index: 848322 (C4 (Web Text))

Max Activating Token Index: 315

Text #6

Max Range: 1.3865. Min Range: -1.3865

Max Act: 1.1740. Min Act: -0.0001

Data Index: 282682 (C4 (Web Text))

Max Activating Token Index: 81

Text #7

Max Range: 1.3865. Min Range: -1.3865

Max Act: 1.2307. Min Act: -0.0001

Data Index: 341698 (C4 (Web Text))

Max Activating Token Index: 477

Text #8

Max Range: 1.3865. Min Range: -1.3865

Max Act: 0.9908. Min Act: -0.0001

Data Index: 1104987 (C4 (Web Text))

Max Activating Token Index: 111

Text #9

Max Range: 1.3865. Min Range: -1.3865

Max Act: 1.1993. Min Act: -0.0001

Data Index: 185138 (C4 (Web Text))

Max Activating Token Index: 652

Text #10

Max Range: 1.3865. Min Range: -1.3865

Max Act: 0.9666. Min Act: -0.0001

Data Index: 1555259 (Python Code)

Max Activating Token Index: 693

Text #11

Max Range: 1.3865. Min Range: -1.3865

Max Act: 1.0929. Min Act: -0.0001

Data Index: 1049419 (C4 (Web Text))

Max Activating Token Index: 238

Text #12

Max Range: 1.3865. Min Range: -1.3865

Max Act: 1.1036. Min Act: -0.0001

Data Index: 418243 (C4 (Web Text))

Max Activating Token Index: 445

Text #13

Max Range: 1.3865. Min Range: -1.3865

Max Act: 1.0665. Min Act: -0.0001

Data Index: 1181636 (C4 (Web Text))

Max Activating Token Index: 743

Text #14

Max Range: 1.3865. Min Range: -1.3865

Max Act: 1.0855. Min Act: -0.0001

Data Index: 485275 (C4 (Web Text))

Max Activating Token Index: 526

Text #15

Max Range: 1.3865. Min Range: -1.3865

Max Act: 0.9143. Min Act: -0.0001

Data Index: 776933 (C4 (Web Text))

Max Activating Token Index: 670

Text #16

Max Range: 1.3865. Min Range: -1.3865

Max Act: 1.1880. Min Act: -0.0001

Data Index: 744256 (C4 (Web Text))

Max Activating Token Index: 202

Text #17

Max Range: 1.3865. Min Range: -1.3865

Max Act: 1.1015. Min Act: -0.0001

Data Index: 955563 (C4 (Web Text))

Max Activating Token Index: 922

Text #18

Max Range: 1.3865. Min Range: -1.3865

Max Act: 1.0197. Min Act: -0.0001

Data Index: 983858 (C4 (Web Text))

Max Activating Token Index: 742

Text #19

Max Range: 1.3865. Min Range: -1.3865

Max Act: 1.3150. Min Act: -0.0001

Data Index: 128754 (C4 (Web Text))

Max Activating Token Index: 982